Llama3.1-405B Instruct

Name: Llama3.1-405B Instruct
Author: Facebook AI Research Lab

Foundation modelLlama3.1

Release date: 2024-07-23Updated: 2024-07-23 23:52:57648

Live demo GitHub Hugging Face Compare

Parameters

405B

Context length

128K

Chinese support

Not supported

Reasoning ability

Llama3.1-405B Instruct is an AI model published by Facebook AI Research Lab, released on 2024-07-23, for Foundation model, with 405B parameters, and 128K context length, requiring about 800GB storage, with a 89.20 score on BBH.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Llama3.1-405B Instruct

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

No data

Model type

Foundation model

Modality (in / out)

No data

Release date

2024-07-23

Model file size

800GB

MoE architecture

Total params / Active params

405B / N/A

Knowledge cutoff

No data

Llama3.1-405B Instruct

Open source & experience

Code license

Weights license

- Commercial use permitted

GitHub repo

https://github.com/meta-llama/llama-models/tree/main/models/llama3_1

Hugging Face

https://huggingface.co/meta-llama/Meta-Llama-3.1-405B-Instruct

Live demo

https://www.meta.ai/

Llama3.1-405B Instruct

Official resources

Paper

DataLearnerAI blog

Llama3.1-405B Instruct

API details

API speed

No data

No public API pricing yet.

Llama3.1-405B Instruct

Benchmark Results

Llama3.1-405B Instruct currently shows benchmark results led by MBPP (1 / 28, score 88.60), HumanEval (9 / 39, score 89), MMLU (16 / 66, score 88.60). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.